Reversing control method
Patent Information
- Application Number
- CN202510352107.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-24
- Publication Date
- 2026-09-25
AI Technical Summary
然而，手动控制倒车方向存在驾驶员的视野有限以及操作难度大等困难
[0016]本申请的实施例的倒车控制方案能够参考与障碍物(例如路缘、栅栏、墙壁或其他车辆)关联的倒车参考线来进行倒车，使得自车能够帮助驾驶员在倒车时借助最近的障碍物(例如某一类型的路缘、栅栏等)来调整控制，而不是直接在车道中心线倒车，这样可以满足特殊且要求高的倒车需求。而且，通过识别车辆周围的边界并生成参考线，本申请的实施例的倒车控制方案可显著提高倒车的安全性和效率。
Smart Images
Figure CN122808722A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of intelligent driving, and more specifically, to a reversing control method, an adaptive cruise control method, a computer program product, and an electronic device. Background Technology
[0002] With the development of the automotive industry, Advanced Driver Assistance Systems (ADAS) have been widely used in modern vehicles. These systems provide assistance to drivers through various sensors and algorithms to improve driving safety and convenience. However, existing ADAS products have certain limitations in reversing assistance functions, especially in safe reversing driving under special road conditions. Summary of the Invention
[0003] The inventors of this application recognized that in real-world driving scenarios, when a vehicle restarts after parking and needs to reverse, drivers often want to use the nearest obstacle (such as a curb, fence, wall, or other vehicle) as a reference to adjust the reversing direction. For example, when a vehicle is parked on the side of the road, the driver may reverse along the curb; in a narrow space, the driver may use surrounding walls or other vehicles to avoid a collision. However, manually controlling the reversing direction presents difficulties such as limited driver visibility and high operational complexity. These difficulties result in slower reversing speeds, requiring the driver to frequently adjust direction and speed to avoid collisions. This not only increases the complexity of driving but may also increase the risk of collisions.
[0004] Based on the above understanding, according to one aspect of this application, this application proposes a reversing control method, the method comprising: identifying a boundary of a preset target type; calculating a reversing reference line associated with the identified boundary based on the identified boundary; and planning a reversing trajectory according to the reversing reference line for reversing control.
[0005] As a supplement or replacement to the above scheme, in the above method, the boundary of the preset target type includes: the boundary between the lane and the curb and the boundary between the lane and the fence.
[0006] As a supplement or replacement to the above scheme, in the above method, identifying the boundaries of the preset target type includes: based on sensor input, using online maps or image segmentation algorithms to identify the boundaries of different target types, and representing them in the form of polylines.
[0007] As a supplement or alternative to the above solution, in the above method, the sensor includes a camera, millimeter-wave radar, and LiDAR.
[0008] As a supplement or replacement to the above scheme, in the above method, whether to trigger the boundary of the preset target type is determined based on the vehicle speed, whether there are obstacles behind, and whether there is a reversing reference target.
[0009] As a supplement or replacement to the above scheme, in the above method, the reversing reference line is a vehicle navigation line generated based on the boundary and is expressed in polynomial form (e.g., cubic polynomial).
[0010] As a supplement or replacement to the above solution, in the above method, planning the reversing trajectory for reversing control based on the reversing reference line includes: sampling a target position at a certain distance on the reversing reference line; planning a polynomial trajectory from the current position of the vehicle to the target position; and providing the polynomial trajectory to the corresponding control module to calculate the corresponding steering wheel angle, accelerator, and brake signals.
[0011] According to another aspect of this application, this application proposes an adaptive cruise control method, the method comprising: determining whether the conditions for activating a reversing assist function are met based on the vehicle speed, whether there is an obstacle behind, and whether there is a reversing reference target; and when the conditions for activating the reversing assist function are met, performing the method described above.
[0012] As a supplement or replacement to the above solution, in the above method, if the vehicle speed is greater than the preset speed, there is an obstacle behind, or there is no reversing reference target, it is determined that the conditions for activating the reversing assistance function are not met; otherwise, it is determined that the conditions are met.
[0013] According to another aspect of this application, a computer program product is provided, including a computer program that, when executed by a processor, implements the method described above.
[0014] According to another aspect of this application, a parking controller is provided, the parking controller including a processor, wherein the processor is configured to perform the method described above.
[0015] According to another aspect of this application, an electronic device (such as a domain controller, camera, or radar) is provided, including a memory, a processor, and a computer program stored in the memory, the processor executing the computer program to implement the method described above.
[0016] The reversing control scheme of this application can refer to reversing reference lines associated with obstacles (such as curbs, fences, walls, or other vehicles) to reverse, enabling the vehicle to help the driver adjust control by using the nearest obstacle (such as a certain type of curb, fence, etc.) when reversing, instead of reversing directly on the center line of the lane. This can meet special and demanding reversing needs. Moreover, by identifying the boundaries around the vehicle and generating reference lines, the reversing control scheme of this application can significantly improve the safety and efficiency of reversing. Attached Figure Description
[0017] The above and other objects and advantages of this application will become more fully clear from the following detailed description taken in conjunction with the accompanying drawings, wherein the same or similar elements are denoted by the same reference numerals.
[0018] Figure 1 A flowchart illustrating a reversing control method according to an embodiment of this application is shown;
[0019] Figure 2 A schematic diagram illustrating reversing by generating and tracking reversing reference lines according to an embodiment of this application is shown; and
[0020] Figure 3 A schematic diagram of the structure of an electronic device according to an embodiment of this application is shown. Detailed Implementation
[0021] In the following, longitudinal control schemes according to various exemplary embodiments of the present application will be described in detail with reference to the accompanying drawings.
[0022] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the embodiments of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance. In addition, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples, without contradiction.
[0023] Figure 1 A schematic flowchart of a reversing control method 1000 according to an embodiment of this application is shown. Figure 1 As shown, the method 1000 includes the following steps:
[0024] In step S110, the boundary of the preset target type is identified;
[0025] In step S120, based on the identified boundary, a reversing reference line associated with the boundary is calculated; and
[0026] In step S130, a reversing trajectory is planned based on the reversing reference line in order to perform reversing control.
[0027] In the context of this application, "preset target type boundary" refers to a specific type of boundary that the system pre-sets to identify and process in an automated or assisted driving system (e.g., a reversing assist system). These boundaries are typically environmental features related to vehicle reversing safety and path planning. Specifically, the preset target type boundary may include, but is not limited to, the boundary between a lane and a curb, or the boundary between a lane and a fence. For example, "lane and curb boundary" refers to the boundary between a lane and a curb, i.e., the dividing line between the lane the vehicle is traveling in and the curb on the side of the road, which can be used to help the vehicle drive along the curb when reversing and avoid colliding with roadside obstacles. As another example, "lane and fence boundary" refers to the boundary between a lane and a fence (e.g., a guardrail), i.e., the dividing line between the lane the vehicle is traveling in and the fence on the side of the road, which can be used to help the vehicle drive along the fence when reversing and avoid colliding with the fence or other obstacles.
[0028] In one embodiment, step S110 includes: based on sensor input, using an online map or image segmentation algorithm to identify the boundaries of different target types and representing them as polylines. In one embodiment, the sensor input may come from sensors equipped around the vehicle, such as cameras, millimeter-wave radar, lidar, etc. These sensors can capture environmental information around the vehicle, including images, object distances, speeds, and other data. For example, cameras can capture real-time images of the vehicle's surroundings, providing visual information for target type identification; radar can measure the distance and relative speed between the vehicle and surrounding objects, providing data support for obstacle identification and path planning, etc.
[0029] In one embodiment, an online map refers to dynamically updated map data containing detailed road information, such as the location and shape of lane lines, curbs, fences, buildings, etc. Based on the vehicle's current location and direction of travel, an online map can provide high-precision map information of the surrounding environment in real time, helping to identify target types and boundaries. For example, when a vehicle travels on a road with curbs and fences, an online map can provide detailed map data of that road segment, including the location and shape of the curbs and fences.
[0030] In one embodiment, an image segmentation algorithm is an algorithm in computer vision technology used to segment an image into multiple regions or objects in order to identify and analyze the features of each region. Image segmentation algorithms can process images captured by a camera to segment different targets in the image (such as lane lines, curbs, fences, crosswalks, vehicles, pedestrians, etc.). For example, an image segmentation algorithm can identify lane lines in an image and distinguish them from other targets.
[0031] In one embodiment, the boundaries of different target types refer to the dividing lines between various objects or areas in the environment, such as the boundary between a lane and a curb, or the boundary between a lane and a fence. These boundaries have certain reference value for vehicle reversing and path planning. For example, in the context of this application, by identifying these boundaries, subsequent vehicles can calculate and generate reversing reference lines, thereby reversing more safely based on these reference lines. For example, when reversing at the roadside, the reversing reference lines generated based on the boundary between the lane and the curb can help the vehicle maintain a safe distance from the curb and avoid collisions. In one embodiment, the boundary can be represented by a series of connected straight line segments (i.e., polylines). Representing the boundary with polylines simplifies complex boundary shapes into a series of ordered points, making it easier for computers to process and analyze.
[0032] Step S110 can be determined based on one or more parameters. In one embodiment, the determination of whether to trigger step S110 is based on the vehicle speed, whether there is an obstacle behind, and whether there is a reversing reference target, i.e., identifying the boundary of a preset target type. For example, if the vehicle speed is greater than a preset speed (e.g., 5 km / h to 10 km / h), there is an obstacle behind, or there is no reversing reference target (e.g., no curb or fence is found), step S110 is determined to be triggered; otherwise, it is determined not to be triggered.
[0033] In step S120, a reversing reference line associated with the identified boundary is calculated. Here, the "reversing reference line" guides the vehicle along this line when reversing, aiming to help the vehicle maintain a safe distance from the boundary and avoid collisions with obstacles. In one or more embodiments, the reversing reference line is a boundary-dependent vehicle navigation line and is represented in polynomial form.
[0034] Assuming the vehicle is parked on the roadside, with the curb as the boundary, the system identifies the curb boundary in step S110 and represents it as a polyline. In one embodiment, in step S120, the system needs to calculate the reversing reference line associated with the curb boundary through the following steps:
[0035] First, determine the curb boundary: the key point coordinates of the curb boundary are (x1, y1), (x2, y2), (x3, y3), (x4, y4), (x5, y5), ... (x n ,y n );
[0036] Secondly, determine the safety space (i.e., the safe distance from the boundary to the vehicle outline): Assuming the safety distance is 0.5 meters, the system needs to generate the initial reversing reference line at a position 0.5 meters outside the curb and taking into account the width of the vehicle.
[0037] Next, generate the initial reversing reference lines: offset the key points of the curb boundary along the boundary normal direction by a suitable distance, for example, 0.5 + Width / 2, where Width represents the vehicle width, in order to generate new key points (x1', y1'), (x2', y2'), (x3', y3'), (x4', y4'), (x5', y5'), ... (x n ',y n Connect these new key points to form a new broken line, which is the initial reversing reference line;
[0038] Then, the initial reversing reference line is smoothed and verified. For example, the reversing reference line is smoothed to ensure that the vehicle can drive smoothly when reversing; and the generated reversing reference line is checked to ensure that it meets safety requirements and that the vehicle will not collide with the curb when reversing.
[0039] Finally, the final reversing reference line is optimized and fitted. In one embodiment, a cubic polynomial reference line can be optimized and fitted:
[0040] y = a3x 3 +a2x 2 +a1x+a0.
[0041] In step S130, a reversing trajectory is planned based on the reversing reference line for reversing control. Here, the "reversing trajectory" is a trajectory generated by the planning module of the automatic or assisted driving system to follow the reversing reference line, and this trajectory is provided to downstream control modules (e.g., lateral control module or longitudinal control module) for reversing control.
[0042] In one embodiment, step S130 includes: sampling a target position at a certain distance on a reversing reference line; planning a polynomial trajectory from the current position of the vehicle to the target position; and providing the polynomial trajectory to the corresponding control module to calculate the corresponding steering wheel angle, accelerator, and brake signals.
[0043] For example, suppose a vehicle needs to reverse along a reversing reference line to a designated position. A fifth-order polynomial can be used to fit the path from the vehicle's current position to that designated position (i.e., the target position). Assuming the vehicle's current position is (x0, y0) and the target position is (x1, y1), the polynomial trajectory in the Frenet coordinate system can be represented as:
[0044] d(s)=d5s 5 +d4s 4 +d3s 3 +d2s 2 +d1s+d0,
[0045] By solving for the polynomial coefficients d5, d4, d3, d2, d1, and d0, a smooth trajectory that conforms to the vehicle's dynamic constraints is ensured. Finally, the polynomial trajectory is provided to the lateral control module and the longitudinal control module. The lateral control module calculates the steering wheel angle to ensure the vehicle travels along the trajectory path; the longitudinal control module calculates the throttle and brake signals to ensure the vehicle travels at appropriate speed and acceleration. In this embodiment, by sampling the target position on the reversing reference line, planning the polynomial trajectory, and providing the trajectory to the control module, precise reversing control can be achieved. This method ensures that the vehicle can safely and efficiently travel along the reversing reference line and ultimately reach the target position.
[0046] The reversing control method 1000 of this application can be combined with various autonomous driving or assisted driving functions. In one embodiment, it can be determined whether to activate the reversing assistance (control) function, i.e. whether to execute the reversing control method 1000, based on one or more parameters.
[0047] Taking adaptive cruise control as an example, the method may include: determining whether the conditions for activating the reversing assist function are met based on the vehicle speed, whether there is an obstacle behind, and whether there is a reversing reference target; and when it is determined that the conditions for activating the reversing assist function are met, executing one or more embodiments of the reversing control method 1000 of the present invention (which will not be described again here). In one embodiment, if the vehicle speed is greater than a preset speed (e.g., 5 km / h to 10 km / h), there is an obstacle behind, or there is no reversing reference target (e.g., no curb or fence is found), it is determined that the conditions for activating the reversing assist function are not met; otherwise, it is determined that the conditions are met.
[0048] Figure 2 A schematic diagram illustrating the generation and tracking of reversing reference lines according to an embodiment of this application is shown. Figure 2As shown, vehicle 210 is preparing to reverse. The automatic driving system or driver assistance system installed on vehicle 210 first determines whether to activate the reversing assistance function. For example, this determination may be based on whether conditions such as the vehicle's own speed, whether there are obstacles behind it, and whether there are reference targets are met.
[0049] In one embodiment, the conditions for determining whether the reversing assist function is activated are: (1) the vehicle speed is lower than the preset speed; (2) there are no obstacles behind the vehicle or the obstacles are beyond a safe distance; and (3) there is a reversing target available for reference. All three conditions must be met simultaneously.
[0050] In other words, the following conditions are not met for the reversing assist function to be activated: (1) the vehicle speed is higher than the preset speed; or (2) there is an obstacle behind the vehicle that is relatively close; or (3) there is no reversing target available for reference. If any one of the above three conditions is met, the reversing assist function will not be activated.
[0051] Next, based on the input from multiple cameras surrounding the vehicle 210 (e.g., six cameras: a front camera, a rear camera, a left camera, a right camera, a left rear camera, and a right rear camera), an online map is used to predict some polylines that can serve as roadside boundaries. For example, by combining the camera input, a predicted map can be obtained using the online map, which may include boundaries represented by polylines. This predicted map may also include information such as the vehicle's location, lane center lines, and pedestrian crossing lines.
[0052] refer to Figure 2 In a simple parking scenario, based on boundary 220 and considering a safety space 225 (e.g., set to 0.5m to 1m), a reversing reference line 230 can be calculated or generated. Then, a trajectory can be planned. Figure 2 (Not shown in the image) Follows the reversing reference line 230 as input to the downstream control module. Finally, based on the real-time trajectory, the system controls the vehicle's horizontal and vertical movement and outputs steering wheel and throttle commands, enabling the vehicle 210 to safely and efficiently reach the designated location.
[0053] It should be noted that, although in Figure 2 In the example, boundary 220 is a straight line, but the solution in this application is not limited to this. Figure 2 The example of a straight line should also apply to cases where the boundary or curb itself is curved or irregular. For instance, image segmentation algorithms can identify curved or irregular curbs and represent them as polylines or continuous curves.
[0054] Those skilled in the art will readily understand that the reversing control method provided in one or more embodiments of this application can be implemented by a computer program. For example, the computer program is included in a computer program product, and when the computer program is executed by a processor, it implements the reversing control method of one or more embodiments of this application. As another example, when a computer-readable storage medium (e.g., a USB flash drive) storing the computer program is connected to a computer, running the computer program executes the reversing control method of one or more embodiments of this application.
[0055] According to one aspect of this application, the reversing control method provided by this application can be implemented in a parking controller. For example, the parking controller may include a processor configured to execute the reversing control method of one or more embodiments of this application.
[0056] refer to Figure 3 It shows a structural schematic diagram of an electronic device 3000 according to an embodiment of this application. For example... Figure 3 As shown, the electronic device 3000 includes a memory 310 and a processor 320, on which a computer program is stored. In one embodiment, the processor 320 executes the computer program to implement a reversing control method according to one or more embodiments of this application. In one or more embodiments, the electronic device may be a domain controller, a camera, or a radar.
[0057] In summary, the reversing control scheme of the embodiments of this application can refer to reversing reference lines associated with obstacles (such as curbs, fences, walls, or other vehicles) for reversing, enabling the vehicle to help the driver adjust control by using the nearest obstacle (such as a certain type of curb, fence, etc.) when reversing, instead of reversing directly on the center line of the lane. This can meet special and demanding reversing needs. Moreover, by identifying the boundaries around the vehicle and generating reference lines, the reversing control scheme of the embodiments of this application can significantly improve the safety and efficiency of reversing.
[0058] The above examples primarily illustrate the reversing control scheme of embodiments of this application. Although only some embodiments of this application have been described, those skilled in the art should understand that this application can be implemented in many other forms without departing from its spirit and scope. Therefore, the examples and embodiments shown are considered illustrative rather than restrictive, and this application may cover various modifications and substitutions without departing from the spirit and scope of this application as defined in the claims.
Claims
1. A reversing control method, characterized in that, The method includes: Identify the boundaries of preset target types; Based on the identified boundaries, calculate the reversing reference line associated with the boundaries; and Plan the reversing trajectory based on the reversing reference lines to enable reversing control.
2. The method as described in claim 1, wherein, The boundaries of the preset target type include: the boundary between the lane and the curb, and the boundary between the lane and the fence.
3. The method as described in claim 1 or 2, wherein, The boundaries for identifying preset target types include: Based on sensor input, online maps or image segmentation algorithms are used to identify the boundaries of different target types and represent them as polylines.
4. The method of claim 3, wherein, The sensors include cameras, millimeter-wave radar, and LiDAR.
5. The method of claim 1, wherein, The determination of whether to trigger the boundary of the preset target type is based on the vehicle's speed, whether there are obstacles behind it, and whether there is a reversing reference target.
6. The method of claim 1, wherein, The reversing reference line is a vehicle navigation line generated based on the boundary and is represented in polynomial form.
7. The method of claim 1, wherein, Planning a reversing trajectory based on the reversing reference lines for reversing control includes: Sample a target position at a certain distance along the reversing reference line; Plan a polynomial trajectory from the vehicle's current position to the target position; and The polynomial trajectory is provided to the corresponding control module to calculate the corresponding steering wheel angle, throttle, and brake signals.
8. A method for adaptive cruise control, characterized in that, The method includes: The conditions for activating the reversing assist function are determined based on the vehicle's speed, the presence of obstacles behind it, and the availability of a reversing reference point; and When it is determined that the conditions for activating the reversing assist function are met, the method described in any one of claims 1 to 4, 6 to 7 shall be executed.
9. The method of claim 8, wherein, If the vehicle speed is greater than the preset speed, there is an obstacle behind the vehicle, or there is no reversing reference target, the conditions for activating the reversing assist function are not met; otherwise, the conditions are met.
10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 9.
11. A parking controller, characterized in that, The parking controller includes a processor, wherein the processor is configured to perform the method as described in any one of claims 1 to 7.
12. An electronic device comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the method as described in any one of claims 1 to 9.
13. The electronic device of claim 12, wherein, The electronic device is a domain controller, camera, or radar.